Moonshine: Speech Recognition for Live Transcription and Voice Commands

This paper introduces Moonshine, a family of speech recognition models optimized for live transcription and voice command processing. Moonshine is based on an encoder-decoder transformer architecture and employs Rotary Position Embedding (RoPE) instead of traditional absolute position embeddings. Th...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-10
Main Authors: Jeffries, Nat, King, Evan, Manjunath Kudlur, Nicholson, Guy, Wang, James, Warden, Pete
Format: Article
Language:English
Subjects:
Encoders-Decoders
Error reduction
Real time
Segments
Speech recognition
Voice recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper introduces Moonshine, a family of speech recognition models optimized for live transcription and voice command processing. Moonshine is based on an encoder-decoder transformer architecture and employs Rotary Position Embedding (RoPE) instead of traditional absolute position embeddings. The model is trained on speech segments of various lengths, but without using zero-padding, leading to greater efficiency for the encoder during inference time. When benchmarked against OpenAI's Whisper tiny-en, Moonshine Tiny demonstrates a 5x reduction in compute requirements for transcribing a 10-second speech segment while incurring no increase in word error rates across standard evaluation datasets. These results highlight Moonshine's potential for real-time and resource-constrained applications.
ISSN:2331-8422